Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    oxidation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .iter
    -0.08
    preload
    -0.07
     Anne
    -0.07
    .assertIs
    -0.07
    Anne
    -0.07
     harness
    -0.07
    中に
    -0.06
    %E
    -0.06
     bourgeois
    -0.06
     Roo
    -0.06
    POSITIVE LOGITS
    Lbl
    0.08
    tolua
    0.08
     güc
    0.07
    慝
    0.07
    fdb
    0.07
    取暖
    0.07
     darkest
    0.07
    ält
    0.07
    _snd
    0.07
    outline
    0.07
    Act Density 0.100%

    No Known Activations